Inclusive Technology for Marginalised Languages

Meet the Lab

Francis M. Tyers

English, Spanish, Catalan, French, Norwegian, Russian

morphology, dependency syntax, speech recognition, machine translation, languages of Latin America and Eurasia

Nils Hjortnæs

English, German

Specialty: Speech Recognition, Low Resource languages

Anastasia Kuznetsova

Russian, English, Portuguese, Spanish, Lithuanian

speech recognition, speech enhancement, reinforcement learning, computational morphology

Esra Önal

Turkish, English

morphology, languages of Turkey

Nicholas Howell

English, Russian

machine learning, morphology, finite-state transducers

Anurag Kumar

English, Hindi

Deep Learning Systems, Speech Recognition, Reinforcement learning, NLP

Daniel Swanson

English, Spanish, Hebrew

machine translation, finite-state morphology, parsing

Every person in the world should have access to their technology in their own, native language.

Projects

Language technology for Western Sierra Nahuatl

Reinforcement-based curriculum learning

Speech technology for language learning

Language technology for Kʼicheʼ

Predictive text entry for polysynthetic languages

Unsupervised pretraining for speech recognition

Publications

2021

Park, H., Tyers, F. M. and Schwartz, L. (2021) "Universal Dependencies for St. Lawrence Island Yupik". Proceedings of the First Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). pp.
Pugh, R. and Tyers, F. M. (2021) "Investigating variation in written forms of Nahuatl using character-based language models". Proceedings of the First Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). pp.
Kuznetsova, A. and Tyers, F. M. (2021) "A morphological analyser for Paraguayan Guaraní". Proceedings of the First Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). pp.
Howell, N. and Tyers, F. M. (2021) "A survey of part-of-speech tagging approaches applied to Kʼicheʼ". Proceedings of the First Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). pp.
Tyers, F. M. and Henderson, R. (2021) "A corpus of Kʼicheʼ annotated for morphosyntactic structure". Proceedings of the First Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). pp.
Richardson, I. and Tyers, F. M. (2021) "A morphological analyser for Kʼicheʼ". Procesamiento de Lenguaje Natural. No. 66, pp. 99—109
Pugh, R., Tyers, F. M., and Huerta Mendez, M. (2021) "Towards an Open Source Finite-State Morphological Analyzer for Zacatlán-Ahuacatlán-Tepetzintla Nahuatl". Proceedings of ComputEL4 pp.
Kuznetsova, A., Kumar, A. and Tyers, F. M. (2021) "A bandit approach to curriculum generation for automatic speech recognition". arXiv:2102.03662 [cs.CL]
Hjortnæs, N., Partanen, N., Rießler, M. and Tyers, F. M. (2021) "The Relevance of the Source Language in Transfer Learning for ASR". Proceedings of ComputEL4 pp.

2020

Tyers, F. M. and Nicholas Howell (2020) "Morphological analysis and disambiguation for Breton". Language Resources and Evaluation. doi://10.1007/s10579-020-09510-8
Hjortnæs, N., Arkhangelskiy, T., Partanen, N., Rießler, M. and Tyers, F. M. (2020) "Improving the Language Model for Low-Resource ASR with Online Text Corpora". Proceedings of the 1st Joint SLTU and CCURL Workshop (SLTU-CCURL 2020). 336—341
Zueva, A., Kuznetsova, A. and Tyers, F. M. (2020) "A Finite-State Morphological Analyser for Evenki". Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020). 2574—2582
Hjortnæs, N., Partanen, N., Rießler, M. and Tyers, F. M. (2020) "Towards a Speech Recognizer for Komi, an Endangered and Low-Resource Uralic Language". Proceedings of the 6th International Workshop on Computational Linguistics of Uralic Languages pp.

2019

Önal, E. and Tyers, F. M. (2019) "Building a morphological analyser for Laz". Proceedings of Recent Advances in Natural Language Processing.